TIGER: Taming Identity, Geometry, and Generative Priors for High-Quality Face Video Restoration

2026-06-23

AI Summary

This work addresses the challenge of simultaneously preserving identity fidelity, disentangling viewpoint variations, and achieving perceptual realism in face video restoration. To this end, the authors propose TIGER, a novel framework that jointly models identity, geometric, and generative priors for the first time. TIGER anchors identity through embedded identity injection, decouples viewpoint via 2D-to-3D geometric lifting, and efficiently leverages generative prior through a one-step rectified flow module, all trained under a three-stage progressive strategy. The study introduces a large-scale Face Video Restoration (FVR) dataset to enable systematic evaluation. Extensive experiments demonstrate that TIGER achieves state-of-the-art performance in identity preservation, temporal consistency, and visual realism, significantly advancing both the quality and efficiency of face video restoration.

Abstract

Face Video Restoration (FVR) aims to recover high-fidelity facial videos from degraded input while preserving identity and semantic consistency across frames. Existing methods often struggle to simultaneously address three key challenges: identity shift, viewpoint-entangled guidance, and perceptual realism. To tackle these issues, we propose TIGER, a structured tri-prior fusion framework that Tames Identity, Geometry, and gEnerative pRiors for high-quality FVR. Specifically, an Identity Prior is first established by injecting subject-discriminative embeddings into the latent space, effectively anchoring the subject's identity against severe degradations. Then, to provide temporally consistent structural guidance for dynamic videos, TIGER constructs a Geometry Prior by lifting 2D reference cues into a disentangled 3D parameter space, creating a geometric anchor through cross-source parameter fusion. Moreover, to achieve maximum efficiency without compromising realism, we harness the video generation model's Generative Prior through a one-step rectified flow. We further design a progressive three-stage training optimization strategy that refines structural fidelity, textural reconstruction, and distribution-level realism to ensure robust optimization. We also construct a large-scale FVR dataset to facilitate robust training and standardized evaluation. Extensive experiments demonstrate that TIGER achieves state-of-the-art performance in both identity fidelity and temporal stability, delivering a high-quality, efficient and identity-consistent FVR. Project page: https://yzhoulv.github.io/Tiger/.

Problem

• Face Video Restoration
• Identity Shift
• Viewpoint-Entangled Guidance
• Perceptual Realism

Innovation

• Identity Prior
• Geometry Prior
• Generative Prior
• Rectified Flow
• Face Video Restoration